• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.6
• /
• pp.67-75
• /
• 1998

Although the nCE(n-th order cross-entropy) error function resolves the incorrect saturation problem of conventional EBP(error back-propagation) algorithm, the performance of MLP's (multilayer perceptrons) trained using the nCE function depends heavily on the order of the nCE function. In this paper, we propose an adaptive learning rate to make the performance of MLP's insensitive to the order of the nCE error. Additionally, we propose a limited error signal of output node to prevent unstable learning due to the adaptive learning rate. The effectiveness of the proposed method is demonstrated in simulations of handwritten digit recognition and thyroid diagnosis tasks.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.82-89
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.110-114
• /
• 2010

We describe a new method for text categorization using TextRank algorithm. Text categorization is a problem that over one pre-defined categories are assigned to a text document. TextRank algorithm is a graph-based ranking algorithm. If we consider that each word is a vertex, and co-occurrence of two adjacent words is a edge, we can get a graph from a document. After that, we find important words using TextRank algorithm from the graph and make feature which are pairs of words which are each important word and a word adjacent to the important word. We use classifiers: SVM, Na$\ddot{i}$ve Bayesian classifier, Maximum Entropy Model, and k-NN classifier. We use non-cross-posted version of 20 Newsgroups data set. In consequence, we had an improved performance in whole classifiers, and the result tells that is a possibility of TextRank algorithm in text categorization.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.183-187
• /
• 2005

In this paper, we propose a heuristic method to select features using a Two-Phase Markov Blanket-based (TPMB) algorithm. The first phase, filtering phase, of TPMB algorithm works by filtering the obviously redundant features. A non-linear correlation method based on Information theory is used as a metric to measure the redundancy of a feature [1]. In second phase, approximating phase, the Markov Blanket (MB) of a system is estimated by employing the concept of cross entropy to identify the MB. We perform experiments on microarray data and report two popular dataset, AML-ALL [3] and colon tumor [4], in this paper. The experimental results show that the TPMB algorithm can significantly reduce the number of features while maintaining the accuracy of the classifiers.

• Journal of Broadcast Engineering
• /
• v.7 no.4
• /
• pp.291-299
• /
• 2002

This paper proposes an efficient motion compensation algorithm for video sequences with brightness variations. In the proposed algorithm, the brightness variation parameters are estimated and local motions are compensated. To detect the frame with large brightness variations. we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than the conventional methods, with a low computational load, when the video scene contains large brightness changes.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.57-62
• /
• 2010

Recently, decision tree techniques have been studied in terms of quick searching and extracting of massive data in medical fields. Although many different techniques have been developed such as CART, C4.5 and CHAID which are belong to a pie in Clermont decision tree classification algorithm, those methods can jeopardize remained data by the binary method during procedures. In brief, C4.5 method composes a decision tree by entropy levels. In contrast, CART method does by entropy matrix in categorical or continuous data. Therefore, we compared C4.5 and CART methods which were belong to a same pie using breast cancer data to evaluate their performance respectively. To convince data accuracy, we performed cross-validation of results in this paper.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.9
• /
• pp.952-958
• /
• 2014

In this paper, we propose a parametric sparse recovery algorithm(SRA) applied to a radar signal model, based on the compressive sensing(CS), for the ISAR(Inverse Synthetic Aperture Radar) image reconstruction from an incomplete radar-cross-section(RCS) data and for the estimation of rotation rate of a target. As the SRA, the iteratively-reweighted-least-square(IRLS) is combined with the radar signal model including chirp components with unknown chirp rate in the cross-range direction. In addition, the particle swarm optimization(PSO) technique is considered for searching correct parameters related to the rotation rate. Therefore, the parametric SRA based on the IRLS can reconstruct ISAR image and estimate the rotation rate of a target efficiently, although there exists missing data in observed RCS data samples. The performance of the proposed method in terms of image entropy is also compared with that of the traditional interpolation methods for the incomplete RCS data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1046-1052
• /
• 2021

Artificial intelligence is being applied in various industrial fields to the development of the fourth industry and the construction of high-performance computing environments. In the medical field, deep learning learning such as cancer, COVID-19, and bone age measurement was performed using medical images such as X-Ray, MRI, and PET and clinical data. In addition, ICT medical fusion technology is being researched by applying smart medical devices, IoT devices and deep learning algorithms. Among these techniques, medical image-based deep learning learning requires accurate finding of medical image biomarkers, minimal loss rate and high accuracy. Therefore, in this paper, we would like to compare and analyze the performance of the Cross-Entropy function used in the image classification algorithm of the loss function that derives the loss rate in the chest X-Ray image-based deep learning learning process.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.3
• /
• pp.291-297
• /
• 2012

Conventional Fourier analysis can give only limited information about the dynamic characteristics of nonstationary signals. Instead, time-frequency analysis is widely used to investigate the nonstationary signal in detail. Several time-frequency analysis methods are compared for a typical acoustic emission burst generated during the impact between a ferrite ceramic and aluminum plate. This AE burst is inherently nonstationary and random containing many frequency contents, which leads to severe interference between cross terms in bilinear convolution type distributions. The smoothing and reassignment processes can improve the readability and resolution of the results. Spectrogram and scalogram of the AE burst are obtained and compared to get the characteristics information. Renyi entropies are computed for various bilinear time-frequency transforms to evaluate the randomness. These bilinear transforms are reassigned by using the improved algorithm in discrete computation.